Kuaishou

Kuaishou is a large-scale short-video recommendation system dataset used to evaluate the effectiveness of generative retrieval methods in producing high-quality candidate recommendations under strict latency constraints.

Papers using Kuaishou (11)

DualGR: Generative Retrieval with Long and Short-Term Interests Modeling2025LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation2025Breaking the Likelihood Trap: Consistent Generative Recommendation with Graph-structured Model2025MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction2025From Generation to Consumption: Personalized List Value Estimation for Re-ranking2025OneRec-V2 Technical Report2025Stratified Expert Cloning for Retention-Aware Recommendation at Scale2025AlignPxtr: Aligning Predicted Behavior Distributions for Bias-Free Video Recommendations2025KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems2022 · 235 citesFeature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation2022 · 51 citesDisentangled Causal Embedding With Contrastive Learning For Recommender System2023 · 20 cites